carve-harness: Skill for Claude Code

.claude/skills/anti-ai-slop/SKILL.md

anti-ai-slop is a skill for Claude Code from claude-code-expert/carve-harness. It costs 194 tokens per session (2,699 once invoked), scanned A, original, MIT.

A quality-checking skill for visual outputs and written material, including images, HTML, SVG, slides, PDFs, documents, reports, and marketing copy.

In plain words
What is it for?
Use it before creating or editing visual or written deliverables to check hierarchy, spacing, typography, evidence, and restraint.
Why use it?
It filters out common AI design and writing patterns, such as excessive decoration, generic wording, repetitive structure, and too many bullet points.

Skill for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths.

This is claude-code-expert/carve-harness's own configuration. It tells Claude Code how to work on carve-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything carve-harness configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .claude/hooks/check-slop.mjs <파일> [<파일> ...].

Reuse

Borrowing it

Nothing to install: this file belongs to claude-code-expert/carve-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/claude-code-expert/carve-harness/main/.claude/skills/anti-ai-slop/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/claude-code-expert/carve-harness

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for anti-ai-slop

README.md
[![agentmods](https://agentmods.dev/badge/skills/claude-code-expert/carve-harness/anti-ai-slop/github.svg)](https://agentmods.dev/skills/claude-code-expert/carve-harness/anti-ai-slop)
Your own site
<a href="https://agentmods.dev/skills/claude-code-expert/carve-harness/anti-ai-slop"><img src="https://agentmods.dev/badge/skills/claude-code-expert/carve-harness/anti-ai-slop/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for anti-ai-slop

Your own site · 80×15
<a href="https://agentmods.dev/skills/claude-code-expert/carve-harness/anti-ai-slop"><img src="https://agentmods.dev/badge/skills/claude-code-expert/carve-harness/anti-ai-slop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 194 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,699 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00194 $0.02699
Opus 5 $0.00097 $0.01350
Sonnet 5 $0.00039 $0.00540
Haiku 4.5 $0.00019 $0.00270

Measured 3d ago against content hash bac7e7f4d871, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

anti-ai-slop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/anti-ai-slop/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anti-AI-Slop — 고급 산출물 품질 게이트

목표는 "AI가 만든 티를 숨기는 것"이 아니라, 판단을 담아 만드는 것이다. Slop은 판단이 빠진 자리를 장식·상투어·균질 구조가 메꾼 결과다. 판단(무엇을 강조하고, 무엇을 버리고, 왜 이 선택인가)을 넣으면 티는 자연히 사라지고 결과는 시니어 실무자의 산출물과 구분되지 않는다.

핵심 원칙 (모든 범위 공통)

  • 모든 요소는 "이게 무슨 정보를 전달하는가"에 답할 수 있어야 한다. 답 못 하면 삭제한다. 장식·상투어·뱃지·불릿·형용사 전부에 적용된다.
  • 품질은 더함이 아니라 뺌으로 만든다. 그라데이션·글로우·이모지·과장어를 빼고, 위계·여백·근거·구체 명사를 남긴다.
  • 균질함은 기계의 지문이다. 모든 섹션이 같은 길이, 모든 리스트가 같은 항목 수, 모든 문단이 같은 리듬이면 사람이 쓴 게 아니다. 의도적으로 비대칭하게 만든다.

0. 이 파일과 references/의 경계

이 SKILL.md는 즉시 발화하는 하드 게이트다 — 무엇이 금지·강제인지만 담는다. references를 읽지 않아도 §1의 금지·강제는 그대로 적용된다.

references/는 크래프트 정본이다 — 어떻게 만드는지(수치 기준·기법·교정 예시·유형별 제약). 산출물을 만들기 직전 해당 파일을 읽는다. 규칙의 상세는 references에만 두고 여기서 반복하지 않는다.

언제 읽을 파일
모든 시각 작업 (공통 크래프트) references/visual-craft.md
문서·리포트·카피 글쓰기 references/writing-tells.md
카드뉴스 (SNS 정사각·세로) references/card-news.md
HTML 리포트 (장문·분석·데이터) references/html-report.md
슬라이드·PDF (16:9 데크) references/slides-pdf.md
SVG 다이어그램·일러스트 references/svg-image.md

1. 하드 게이트 — 즉시 적용

MUST NOT (금지)

  • 그라데이션 일체 금지linear-gradient · radial-gradient · conic-gradient. 배경·채움·텍스트(background-clip:text) 전부. 특히 보라/핑크 계열.
  • 글로우·컬러 그림자 금지 — 색 들어간 box-shadow, 광택 inset 링, blur ≥ 20px 그림자, backdrop-filter: blur(글래스모피즘).
  • 장식 모션 금지 — hover 시 transform: translate/scale, 로드 시 fade/stagger, pulse·shimmer·float·glow 키프레임. transition은 색·투명도 등 기능적 상태 변화에만, 150ms 이하.
  • 배경 장식 금지 — 거대 반투명 워터마크, 닷·그리드 배경, 페이드 마스크, 광선.
  • 카드 컬러 액센트 바 금지 — 상·하·좌·우 어느 변이든 굵은 컬러 보더로 꾸미기(border-top: Npx solid color). 구분은 전체 1px 보더·여백·라벨로.
  • 이모지 불릿·장식 금지, 뱃지/pill 남발 금지.
  • 마케팅 보일러플레이트 금지 — 과장 상투어 전반. 단어 목록은 린터 marketing 룰과 references/writing-tells.md §1이 정본이다(이 파일에 나열하면 규칙 문서 자신이 걸린다).

MUST (강제)

  • : 무채색(흰/회/검) 베이스 + 액센트 1색. 색은 의미(상태·위계)에만 쓴다.
  • 그림자: 쓰더라도 중성 회색 1단계만 (0 1px 2px rgba(0,0,0,.06)). 없어도 좋다.
  • 구획: 효과 대신 1px solid border + 여백으로 나눈다.
  • 모서리: border-radius 0~8px.
  • 위계: 크기·굵기·여백·정렬로 만든다. 색·효과로 만들지 않는다.
  • 폰트: Inter/Roboto/Arial/system-ui로 기본 수렴 금지. 목적에 맞는 폰트를 의도적으로 고르고 이유를 코드 주석 한 줄로 밝힌다.
  • 접근성: 본문 대비 4.5:1, 큰 텍스트 3:1 이상 (WCAG 2.1 AA). 색만으로 상태를 구분하지 않는다.

Read the full file on GitHub · 145 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago Changed · +26 lines · +25 tokens per session bac7e7f4d871
  2. 11d ago First seen · 119 lines · 169 tokens per session scan A 017295bea5b0

Subscribe to this mod's changes

anti-ai-slop is a skill published in the GitHub repository claude-code-expert/carve-harness (14 stars, last pushed today), licensed MIT. It adds 194 tokens to every session and 2,699 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 50 tokens

accessibility

Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.

microsoft/hve-core · 47 tokens

make-resume

A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.

Hisn00w/ASu-skills · 86 tokens